News

Biostate AI Unveils Breakthrough RNA Sequencing Tools

• By John K. Waters
• 07/17/2024

Biostate AI, a scalable biodata foundry startup, has emerged from stealth mode with the launch of two products: Total RNA sequencing and Copilot for RNAseq data analysis. The company aims to partner with academic researchers, hospital biorepositories, and pharma/biotech companies, leveraging these new products for scalable "multiomic" data collection, scientific discovery, and AI training. (Multinomics refers to the type of biological analysis in which the data sets are multiple "omes," such as the genome, proteome, transcriptome, epigenome, metabolome, and microbiome.)

New Technologies for Comprehensive RNA Analysis
Biostate's Total RNA sequencing employs its patent-pending Barcode-Integrated Reverse Transcription (BIRT) technology. This approach allows for affordable, scalable, and comprehensive analysis of all RNA types, the company says, unlike traditional RNA sequencing, which typically captures only messenger RNA. The new method enables the study of all known RNA species, including biologically significant non-coding RNAs like long non-coding RNAs (lncRNAs), micro RNAs (miRNAs), circular RNAs (circRNAs), and enhancer RNAs (eRNAs).

"The successful training of any AI well requires large quantities of relevant and high-quality data," David Zhang, co-founder and CEO of Biostate AI, said in a statement. "Biostate AI has developed the instrumental technologies to facilitate the collection of more biological data at lower costs. We are pleased to offer these capabilities to academic and industry partners and collaborators."

Expanding Technological Horizons
Biostate AI has filed nine pending patents on its technologies and collaborates with several industry partners, including Twist Bioscience, for new technology development. The company recently in-licensed additional intellectual property from the California Institute of Technology (Caltech) to expand the range of biomolecules analyzed. These advancements are expected to reduce animal testing in preclinical studies conducted by pharma and biotech companies.

"AI is the next frontier and AI needs data, and biological data is a lot harder to get than text or images," said Haomiao Huang, Founding Partner at  Matter Venture Partners, which led the initial funding round for Biostate AI. "We are excited about the potential for Biostate's technology to dramatically lower the cost of collecting RNAseq datasets."

Introducing OmicsWeb Copilot
Biostate AI also launched OmicsWeb Copilot, a conversational AI tool designed to assist biologists in analyzing and visualizing data. Utilizing advanced large-language models (LLMs), Copilot understands user requests and builds customized software and scripts for data analysis. The platform offers access to over 1000 unique RNAseq datasets and is fine-tuned on 5000 proprietary datasets, enabling advanced analyses and anomaly detection. Importantly, Biostate AI offers Copilot at no cost to academic and nonprofit researchers.

"Bioinformatic analysis of RNAseq and other omics data is a highly complex, multi-step process that currently takes many hours of dedicated specialized programming," said Ashwin Gopinath, co-founder and CTO of Biostate AI, in a statement. "We started building OmicsWeb Copilot as an internal tool to help our scientists make sense of the data. Now, we’re opening it up to the general public for free."

A Vision for the Future
Biostate AI aims to develop AI capable of predicting health changes, including toxicity and efficacy responses to drugs. The team has shown that RNA expression in blood from rats before drug dosing can predict survival, with a Hazard Ratio of 8. Scaling this proof-of-concept to human applications will require extensive data collection and analysis, involving petabytes of RNAseq and other omics data.

Founded in 2023, Biostate AI is based in Palo Alto, CA, and Houston, TX. The company collaborates with academic, nonprofit, and industry partners to advance technology development and multiomic biodata collection. Interested parties can reach out at [email protected] for collaboration opportunities.